{"id":"https://openalex.org/W4319790622","doi":"https://doi.org/10.1109/slt54892.2023.10022960","title":"Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-to-End Automatic Speech Recognition","display_name":"Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-to-End Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319790622","doi":"https://doi.org/10.1109/slt54892.2023.10022960"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022960","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089101632","display_name":"Aleksandr Laptev","orcid":"https://orcid.org/0000-0002-4690-705X"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["RU","US"],"is_corresponding":false,"raw_author_name":"Aleksandr Laptev","raw_affiliation_strings":["NVIDIA,USA","ITMO University, St. Petersburg, Russia","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"ITMO University, St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1779,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89353136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6588727235794067},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5470857620239258},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5377111434936523},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5346502661705017},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5136005878448486},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.484425812959671},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.4708744287490845},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4535731375217438},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4483918249607086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43257948756217957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39226043224334717},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32311952114105225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2509642243385315},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24866831302642822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6588727235794067},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5470857620239258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5377111434936523},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5346502661705017},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5136005878448486},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.484425812959671},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.4708744287490845},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4535731375217438},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4483918249607086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43257948756217957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39226043224334717},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32311952114105225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2509642243385315},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24866831302642822},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022960","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W34303869","https://openalex.org/W1494198834","https://openalex.org/W1932198206","https://openalex.org/W1983874169","https://openalex.org/W2028125409","https://openalex.org/W2033875152","https://openalex.org/W2034537249","https://openalex.org/W2095629250","https://openalex.org/W2124558353","https://openalex.org/W2127141656","https://openalex.org/W2127499922","https://openalex.org/W2130799511","https://openalex.org/W2134659216","https://openalex.org/W2152575748","https://openalex.org/W2159391028","https://openalex.org/W2219249508","https://openalex.org/W2254249950","https://openalex.org/W2531327146","https://openalex.org/W2939216642","https://openalex.org/W2955117616","https://openalex.org/W2963931415","https://openalex.org/W2972953886","https://openalex.org/W2974231335","https://openalex.org/W3015634748","https://openalex.org/W3026041220","https://openalex.org/W3097375352","https://openalex.org/W3097777922","https://openalex.org/W3150122400","https://openalex.org/W3161324588","https://openalex.org/W3163169798","https://openalex.org/W3165396901","https://openalex.org/W3196548933","https://openalex.org/W3197451691","https://openalex.org/W4210424357","https://openalex.org/W4287252240","https://openalex.org/W6607114211","https://openalex.org/W6638523607","https://openalex.org/W6638749077","https://openalex.org/W6679825567","https://openalex.org/W6688816777","https://openalex.org/W6693516855","https://openalex.org/W6728622933","https://openalex.org/W6767671539","https://openalex.org/W6789528646","https://openalex.org/W6792850982","https://openalex.org/W6894311372"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W2944691285","https://openalex.org/W2047632477","https://openalex.org/W3041490575","https://openalex.org/W2970690932","https://openalex.org/W4321135767","https://openalex.org/W2069619724"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,30,72],"class":[4],"of":[5,84],"new":[6],"fast":[7],"non-trainable":[8],"entropy-based":[9],"confidence":[10,31,82,93,112],"estimation":[11,113],"methods":[12,51],"for":[13,38,124],"automatic":[14],"speech":[15],"recognition.":[16],"We":[17,89],"show":[18,100],"how":[19],"per-frame":[20,64,118],"entropy":[21],"values":[22],"can":[23],"be":[24],"normalized":[25],"and":[26,35,43,77,86,99,107,126],"aggregated":[27],"to":[28,56,105],"obtain":[29],"measure":[32],"per":[33,36],"unit":[34],"word":[37],"Connectionist":[39],"Temporal":[40],"Classification":[41],"(CTC)":[42],"Recurrent":[44],"Neural":[45],"Network":[46],"Transducer":[47],"(RNN-T)":[48],"models.":[49],"Proposed":[50],"have":[52,71],"similar":[53],"computational":[54],"complexity":[55],"the":[57,62,81,91,116],"traditional":[58],"method":[59],"based":[60,114],"on":[61,95,115],"maximum":[63,117],"probability,":[65],"but":[66],"they":[67,102],"are":[68,103],"more":[69],"adjustable,":[70],"wider":[73],"effective":[74],"threshold":[75],"range,":[76],"better":[78,110],"push":[79],"apart":[80],"distributions":[83],"correct":[85],"incorrect":[87,122],"words.":[88],"evaluate":[90],"proposed":[92],"measures":[94],"LibriSpeech":[96],"test":[97],"sets,":[98],"that":[101],"up":[104],"2":[106],"4":[108],"times":[109],"than":[111],"probability":[119],"at":[120],"detecting":[121],"words":[123],"Conformer-CTC":[125],"Conformer-RNN-T":[127],"models,":[128],"respectively.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}